google_ai: Support Gemini 3.5 Flash#57299
Merged
Merged
Conversation
tomhoule
commented
May 20, 2026
22b3a91 to
46f804a
Compare
tomhoule
commented
May 20, 2026
46f804a to
0c69f2a
Compare
Implements the [official upgrade instructions](https://ai.google.dev/gemini-api/docs/whats-new-gemini-3.5#migrate-from-3-flash-preview) for Gemini 3.5 Flash, and adds BYOK support. For all Gemini 3 and 3.5 series models, the client now utilizes the newer `thinking_level` parameter instead of `thinking_budget` inside the serialized `ThinkingConfig` and avoids serializing the no-longer-recommended parameters `temperature`, `top_p`, and `top_k`. `FunctionCall` and `FunctionResponse` now support passing an `id` to properly maintain chain-of-thought preservation and match execution IDs across turns. When resolving incoming tool uses, the mapper prefers the execution ID returned by Gemini, falling back to sequential naming in other scenarios. Release Notes: - Added support for Gemini 3.5 Flash in the Google AI model provider.
0c69f2a to
7a5b777
Compare
tomhoule
commented
May 20, 2026
tomhoule
commented
May 20, 2026
rtfeldman
approved these changes
May 20, 2026
edwbaeza96
approved these changes
May 21, 2026
Member
|
/cherry-pick preview |
zed-zippy Bot
added a commit
that referenced
this pull request
May 21, 2026
…#57373) Cherry-pick of #57299 to preview ---- Implements the [official upgrade instructions](https://ai.google.dev/gemini-api/docs/whats-new-gemini-3.5#migrate-from-3-flash-preview) for Gemini 3.5 Flash, and adds BYOK support. The changes about thinking_level and temperature apply to our situation, but they are only recommendations, and we have to support older models, so I preferred not trying to force the preferred / remove the discouraged parameters for now. `temperature` becomes optional - we don't fill in a default anymore, since passing it is now discouraged. This commit also adds support for `thinking_level`, since it is now preferred to `thinking_budget`. `FunctionCall` and `FunctionResponse` now support passing an `id` to properly maintain chain-of-thought preservation and match execution IDs across turns. When resolving incoming tool uses, the mapper prefers the execution ID returned by Gemini, falling back to sequential naming in other scenarios. Release Notes: - Added support for Gemini 3.5 Flash in the Google AI model provider. Co-authored-by: Tom Houlé <13155277+tomhoule@users.noreply.github.com>
Member
|
/cherry-pick stable |
zed-zippy Bot
added a commit
that referenced
this pull request
May 21, 2026
…57392) Cherry-pick of #57299 to stable ---- Implements the [official upgrade instructions](https://ai.google.dev/gemini-api/docs/whats-new-gemini-3.5#migrate-from-3-flash-preview) for Gemini 3.5 Flash, and adds BYOK support. The changes about thinking_level and temperature apply to our situation, but they are only recommendations, and we have to support older models, so I preferred not trying to force the preferred / remove the discouraged parameters for now. `temperature` becomes optional - we don't fill in a default anymore, since passing it is now discouraged. This commit also adds support for `thinking_level`, since it is now preferred to `thinking_budget`. `FunctionCall` and `FunctionResponse` now support passing an `id` to properly maintain chain-of-thought preservation and match execution IDs across turns. When resolving incoming tool uses, the mapper prefers the execution ID returned by Gemini, falling back to sequential naming in other scenarios. Release Notes: - Added support for Gemini 3.5 Flash in the Google AI model provider. Co-authored-by: Tom Houlé <13155277+tomhoule@users.noreply.github.com>
This was referenced May 22, 2026
TomPlanche
pushed a commit
to TomPlanche/zed
that referenced
this pull request
Jun 2, 2026
Implements the [official upgrade instructions](https://ai.google.dev/gemini-api/docs/whats-new-gemini-3.5#migrate-from-3-flash-preview) for Gemini 3.5 Flash, and adds BYOK support. The changes about thinking_level and temperature apply to our situation, but they are only recommendations, and we have to support older models, so I preferred not trying to force the preferred / remove the discouraged parameters for now. `temperature` becomes optional - we don't fill in a default anymore, since passing it is now discouraged. This commit also adds support for `thinking_level`, since it is now preferred to `thinking_budget`. `FunctionCall` and `FunctionResponse` now support passing an `id` to properly maintain chain-of-thought preservation and match execution IDs across turns. When resolving incoming tool uses, the mapper prefers the execution ID returned by Gemini, falling back to sequential naming in other scenarios. Release Notes: - Added support for Gemini 3.5 Flash in the Google AI model provider.
This was referenced Jun 3, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Implements the official upgrade instructions for Gemini 3.5 Flash, and adds BYOK support.
The changes about thinking_level and temperature apply to our situation, but they are only recommendations, and we have to support older models, so I preferred not trying to force the preferred / remove the discouraged parameters for now.
temperaturebecomes optional - we don't fill in a default anymore, since passing it is now discouraged.This commit also adds support for
thinking_level, since it is now preferred tothinking_budget.FunctionCallandFunctionResponsenow support passing anidto properly maintain chain-of-thought preservation and match execution IDs across turns. When resolving incoming tool uses, the mapper prefers the execution ID returned by Gemini, falling back to sequential naming in other scenarios.Release Notes: